© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 70888
    Prev
    Next
    INDEX
    Explanations

    words related to design and artistic expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istan
    -0.06
    .usermodel
    -0.06
     pec
    -0.06
    @\
    -0.06
    edef
    -0.06
    opp
    -0.06
    ç¨ĭ
    -0.06
     pari
    -0.06
    246
    -0.06
    argent
    -0.06
    POSITIVE LOGITS
    ystack
    0.08
    ÌĨ
    0.07
    #ac
    0.06
     å¾ĴæŃ©
    0.06
    ieving
    0.06
     вд
    0.06
    باÙĦ
    0.06
    ucker
    0.06
     ,↵
    0.06
    plet
    0.06
    Activations Density 0.000%

    No Known Activations